{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,22]],"date-time":"2026-10-22T16:53:40Z","timestamp":1792688020176,"version":"4.5.0"},"reference-count":59,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"11","license":[{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"funder":[{"name":"Honda, Hyundai, NSF","award":["2339096"],"award-info":[{"award-number":["2339096"]}]},{"name":"ONR","award":["N00014-21-1-2758"],"award-info":[{"award-number":["N00014-21-1-2758"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Robot. Autom. Lett."],"published-print":{"date-parts":[[2026,11]]},"DOI":"10.1109\/lra.2026.3730288","type":"journal-article","created":{"date-parts":[[2026,9,2]],"date-time":"2026-09-02T19:03:59Z","timestamp":1788375839000},"page":"13263-13270","source":"Crossref","is-referenced-by-count":5,"title":["Touch Begins Where Vision Ends: Generalizable Policies for Contact-Rich Manipulation"],"prefix":"10.1109","volume":"11","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-9255-016X","authenticated-orcid":false,"given":"Zifan","family":"Zhao","sequence":"first","affiliation":[{"name":"New York University Shanghai","place":["Shanghai, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4396-653X","authenticated-orcid":false,"given":"Siddhant","family":"Haldar","sequence":"additional","affiliation":[{"name":"New York University","place":["New York, NY, USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1123-5732","authenticated-orcid":false,"given":"Jinda","family":"Cui","sequence":"additional","affiliation":[{"name":"Honda Research Institute USA","place":["San Jose, CA, USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2726-0633","authenticated-orcid":false,"given":"Lerrel","family":"Pinto","sequence":"additional","affiliation":[{"name":"New York University","place":["New York, NY, USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9306-5724","authenticated-orcid":false,"given":"Raunaq","family":"Bhirangi","sequence":"additional","affiliation":[{"name":"New York University","place":["New York, NY, USA"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA55743.2025.11127857"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2025.xxi.010"},{"key":"ref3","article-title":"Improving image generation with better captions","volume-title":"OpenAI","author":"Betker","year":"2023"},{"key":"ref4","article-title":"SAM 2: Segment anything in images and videos","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Ravi"},{"key":"ref5","article-title":"GPT-4 technical report","year":"2023"},{"key":"ref6","first-page":"1","article-title":"End-to-end training of deep visuomotor policies","volume":"17","author":"Levine","year":"2016","journal-title":"J. Mach. Learn. Res."},{"key":"ref7","first-page":"2165","article-title":"RT-2: Vision-language-action models transfer web knowledge to robotic control","volume-title":"Proc. 7th Conf. Robot Learn.","volume":"229","author":"Zitkovich"},{"key":"ref8","first-page":"1282","article-title":"Quantifying generalization in reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Cobbe","year":"2019"},{"key":"ref9","article-title":"A study on overfitting in deep reinforcement learning","author":"Zhang","year":"2018"},{"key":"ref10","article-title":"Mastering visual continuous control: Improved data-augmented reinforcement learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Yarats"},{"key":"ref11","article-title":"Data scaling laws in imitation learning for robotic manipulation","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Lin"},{"key":"ref12","first-page":"26991","article-title":"Behavior generation with latent actions","volume-title":"Proc. 41st Int. Conf. Mach. Learn","volume":"235","author":"Lee"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2023.xix.016"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2023.xix.026"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2024.xx.045"},{"issue":"30","key":"ref16","first-page":"1","article-title":"A review of robot learning for manipulation: Challenges, representations, and algorithms","volume":"22","author":"Kroemer","year":"2021","journal-title":"J. Mach. Learn. Res."},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202133"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1177\/0278364919887447"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/SSCI47803.2020.9308468"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2023.xix.009"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611407"},{"key":"ref22","article-title":"Policy decorator: Model-agnostic online refinement for large policy model","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Yuan"},{"key":"ref23","article-title":"Residual policy learning","author":"Silver","year":"2018"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8794127"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.65109\/icps4845"},{"key":"ref26","article-title":"Residual reinforcement learning from demonstrations","author":"Alakuijala","year":"2021"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1126\/science.aat8414"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2022.104224"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9196976"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1115\/1.3143771"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610835"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2023.3300230"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.3390\/app10196923"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9812312"},{"key":"ref35","first-page":"1722","article-title":"In-hand object rotation via rapid motor adaptation","volume-title":"Proc. Conf. Robot Learn.","author":"Qi","year":"2023"},{"key":"ref36","first-page":"3142","article-title":"Dexterity from touch: Self-supervised pretraining of tactile representations with robotic play","volume-title":"Proc. 7th Conf. Robot Learn","volume":"229","author":"Guzey","year":"2023"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA55743.2025.11128180"},{"key":"ref38","article-title":"A comprehensive survey of image augmentation techniques for deep learning","volume-title":"Pattern Recognit.","volume":"137","author":"Xu","year":"2023"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9812146"},{"key":"ref40","first-page":"1345","article-title":"On-robot learning with equivariant models","volume-title":"Proc. 6th Conf. Robot Learn.","volume":"205","author":"Wang","year":"2023"},{"key":"ref41","first-page":"373","article-title":"Dense object nets: Learning dense visual object descriptors by and for robotic manipulation","volume-title":"Proc. Conf. Robot Learn.","author":"Florence","year":"2018"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3145961"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA55743.2025.11128755"},{"key":"ref44","first-page":"1825","article-title":"Point policy: Unifying observations and actions with key points for robot manipulation","volume-title":"Proc. 9th Conf. Robot Learn","volume":"305","author":"Haldar","year":"2025"},{"key":"ref45","first-page":"1820","article-title":"MimicGen: A data generation system for scalable robot learning using human demonstrations","volume-title":"Proc. 7th Conf. Robot Learn","volume":"229","author":"Mandlekar"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9560942"},{"key":"ref47","first-page":"2372","article-title":"OPEN TEACH: A versatile teleoperation system for robotic manipulation","volume-title":"Proc. 8th Conf. Robot Learn","volume":"270","author":"Iyer"},{"key":"ref48","first-page":"28652","article-title":"Molmo2: Open weights and data for vision-language models with video understanding and grounding","volume-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit.","author":"Clark","year":"2026"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0068"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_37"},{"key":"ref51","article-title":"Green screen augmentation enables scene generalisation in robotic manipulation","author":"Teoh","year":"2024"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/IROS60139.2025.11247097"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA55743.2025.11128638"},{"key":"ref55","article-title":"Learning precise, contact-rich manipulation through uncalibrated tactile skins","author":"Pattabiraman","year":"2024"},{"key":"ref56","article-title":"Continuous control with deep reinforcement learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Lillicrap"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2023.xix.056"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.52202\/079017-4484"},{"key":"ref59","first-page":"1577","article-title":"Efficient online reinforcement learning with offline data","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ball","year":"2023"}],"container-title":["IEEE Robotics and Automation Letters"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/7083369\/11690866\/11676051-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/7083369\/11690866\/11676051.pdf?arnumber=11676051","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,13]],"date-time":"2026-10-13T07:01:05Z","timestamp":1791874865000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11676051\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,11]]},"references-count":59,"journal-issue":{"issue":"11"},"URL":"https:\/\/doi.org\/10.1109\/lra.2026.3730288","relation":{},"ISSN":["2377-3766","2377-3774"],"issn-type":[{"value":"2377-3766","type":"electronic"},{"value":"2377-3774","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,11]]}}}